AI Adversarial Specialist - Fully Remote | Upto $22/hr
WFA Digital Insight
The demand for AI safety experts has grown exponentially, with a 25% increase in job postings over the past year. As companies like mercor invest heavily in AI research, the need for specialists who can test and improve AI systems has become paramount. With the rise of remote work, professionals with expertise in AI adversarial work, cybersecurity, and socio-technical probing are in high demand. Before applying, candidates should be aware that fluency in English and Kannada is required, and prior experience in red teaming is preferred. mercor's commitment to innovation and its impressive list of investors make this a unique opportunity for those looking to make a impact in the field.
Job Description
About the Role
The AI Adversarial Specialist role at mercor is a fully remote, contract position that focuses on testing and improving conversational AI models. As a specialist, you will be responsible for identifying vulnerabilities and exploiting biases in AI systems, with the goal of making them more robust and secure. This role is critical in ensuring that AI systems are safe and reliable, and that they do not pose a risk to users or organizations.The day-to-day responsibilities of this role will involve red teaming conversational AI models, generating high-quality human data, and annotating failures and vulnerabilities. You will also be responsible for documenting your findings and producing reports, datasets, and attack cases for customer action.
What You Will Do
- Red team conversational AI models and agents to identify vulnerabilities and biases
- Generate high-quality human data to test and improve AI systems
- Annotate failures and vulnerabilities, and classify systemic risks
- Apply structure using taxonomies, benchmarks, and playbooks to maintain consistent testing
- Document reproducibly and produce reports, datasets, and attack cases for customer action
- Focus on jailbreaks, prompt injections, misuse cases, and bias exploitation
- Collaborate with other teams to develop and implement new testing methodologies
- Stay up-to-date with the latest developments in AI adversarial work, cybersecurity, and socio-technical probing
- Participate in knowledge-sharing activities to improve the overall expertise of the team
What We Are Looking For
- Fluency in English and Kannada
- Prior experience in red teaming, AI adversarial work, cybersecurity, or socio-technical probing
- Ability to explain risks clearly to technical and non-technical stakeholders
- Strong analytical and problem-solving skills
- Experience with creative probing techniques, such as psychology, acting, or writing
- Familiarity with AI and machine learning concepts
- Strong communication and collaboration skills
- Ability to work independently and as part of a remote team
- Prior experience working with conversational AI models is an asset
Nice to Have
- Experience in Adversarial ML, Cybersecurity, or socio-technical risk analysis
- Knowledge of taxonomies, benchmarks, and playbooks for testing AI systems
- Familiarity with cloud-based technologies and collaboration tools
- Certification in AI, cybersecurity, or a related field
Benefits and Perks
- Competitive hourly rate of $20-$22 per hour
- Opportunity to work on cutting-edge AI research projects
- Collaborative and dynamic work environment
- Professional development opportunities, including training and conference attendance
- Flexible working hours and remote work arrangements
- Access to a global network of professionals in the AI and cybersecurity fields
- Health and wellness benefits, including mental health support
- Paid time off and holidays
- Remote stipend to support home office setup and equipment
How to Stand Out
- To stand out in your application, be sure to highlight your prior experience in red teaming, AI adversarial work, or cybersecurity.
- Develop a strong portfolio that showcases your skills and experience in creative probing techniques, such as psychology, acting, or writing.
- Familiarize yourself with the latest developments in AI adversarial work, cybersecurity, and socio-technical probing to demonstrate your expertise.
- Prepare for the AI interview by reviewing your resume and practicing your responses to common interview questions.
- Be prepared to discuss your experience working with conversational AI models and your approach to identifying vulnerabilities and biases.
- Don't be afraid to ask questions during the interview process to demonstrate your interest in the role and the company.
- Research mercor's values and mission to understand the company culture and how you can contribute to it.
This is a remote position listed on WFA Digital, the platform for professionals who work from anywhere. Browse more remote jobs across all categories.